Theofanis Karaletsos

AI Researcher & Executive; Co-founder, Achira.ai

Career. I am a co-founder, board member, and advisor to Achira.ai, at the interface of statistical physics, AI, and biomolecular simulation for drug discovery. Most recently, I served as Head of AI for Science at the Chan Zuckerberg Initiative, where I led AI for virtual cell models and AI × Science. Previously: VP AI at Insitro, Staff Research Scientist at Meta AI, founding member of Uber AI Labs, and researcher at Geometric Intelligence. View more →

Research. My research is driven by a central question: what does it mean for an AI system to have a model of the world — one that is expressive, calibrated, and useful for decision-making? I work across the full AI stack, from the mathematical foundations of probabilistic inference and deep generative models to scalable algorithms and programming abstractions (I co-created Pyro), to their deployment as world models for scientific discovery in biology and physics. I am drawn to problems where methodology and application genuinely constrain each other. View publications →

Generative AI & World Models

Developing the core generative modeling stack — deep latent variable models, diffusion models, autoregressive systems, and probabilistic programs — as a foundation for AI systems that represent and reason about the world, not just pattern-match within it.

Probabilistic Inference & Epistemology

Building principled methods for uncertainty quantification, Bayesian deep learning, and scalable variational inference. Interested in the epistemological question of how AI systems should represent what they know, what they don't, and how new evidence should update beliefs.

Scientific World Models

Applying generative AI to build faithful computational models of biological and physical systems — from virtual cell models and single-cell generative biology to physics-informed AI. The goal is AI that compresses scientific knowledge and generates testable hypotheses, not just predictions.

Drug Discovery & Molecular AI

Bayesian active learning, biomolecular simulation, and structure-informed generative models for therapeutic design. Interested in how world models over molecular systems can accelerate the discovery of new medicines.

Career

2024 – present

Co-founder, Board Member & Advisor

Achira.ai

Building AI-based molecular world models at the interface of statistical physics and biomolecular simulation for drug discovery.

2024 – 2026

Head of AI for Science

Chan Zuckerberg Initiative

Developed the scientific vision and roadmap for virtual cell modeling, built the AI for Science organization from inception, and drove the research program through to execution — producing foundational results across single-cell biology, genomics, and AI-native scientific reasoning.

Nov 2021 – Nov 2023

VP of AI

Insitro

Led AI research and machine learning at a data-driven drug discovery company.

Aug 2020 – Nov 2021

Technical Lead & Staff Research Scientist

Meta / Facebook

Led the UncertainT team on probabilistic machine learning and uncertainty quantification for large scale neural networks.

2016 – 2020

Co-founder & Research Scientist

Uber AI Labs

Co-founded the lab following Uber's acquisition of Geometric Intelligence. Led research in probabilistic ML, Bayesian deep learning, and co-created Pyro.

– 2016

Research Scientist

Geometric Intelligence

Early-stage AI research startup; acquired by Uber in 2016.

Angel Investments

Windscape.ai

AI for wind farm optimization and energy efficiency.

Studio Atelico

On-device AI engine for lifelike characters in video games.

Reasonable.io

AI training systems for superhuman coding using formal verification.

Stealth biotech

Undisclosed.

Selected Publications View all →

AI for Science

Building the Virtual Cell with Artificial Intelligence

C. Bunne*, Y. Roohani*, Y. Rosen*, ..., T. Karaletsos✶, A. Regev✶, E. Lundberg✶, J. Leskovec✶, S.R. Quake✶

Cell, 2024 * equal contribution ✶ co-seniorpaper arXiv '24

A Cross-Species Generative Cell Atlas Across 1.5 Billion Years of Evolution: The TranscriptFormer Single-cell Model

J.D. Pearce, S.E. Simmonds, G. Mahmoudabadi, L. Krishnan, G. Palla, A. Istrate, A. Tarashansky, B. Nelson, O. Valenzuela, D. Li, S.R. Quake✶, T. Karaletsos✶

bioRxiv, 2025 ✶ co-seniorbioRxiv '25

VariantFormer: A Hierarchical Transformer Integrating DNA Sequences with Genetic Variations and Regulatory Landscapes for Personalized Gene Expression Prediction

S. Ghosal, Y. Barhomi, T. Ganapathi, A. Krystosik, L. Krishnan, S. Guntury, D. Li, F.P. Casale, T. Karaletsos

bioRxiv, 2025bioRxiv '25

rbio1: Training Scientific Reasoning LLMs with Biological World Models as Soft Verifiers

A. Istrate, F. Milletari, F. Castrotorres, J.M. Tomczak, M. Torkar, D. Li, T. Karaletsos

NeurIPS 2025 Workshop AI4D3bioRxiv '25

Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder

M. Bereket, T. Karaletsos

NeurIPS 2023paper arXiv '23

Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models

G. Palla, S. Babu, P. Dibaeinia, J.D. Pearce, D. Li, A.A. Khan, T. Karaletsos✶, J.M. Tomczak✶

NeurIPS 2025 Workshop AI4D3 ✶ co-seniorarXiv '25

Machine Learning

Pyro: Deep Universal Probabilistic Programming

E. Bingham, J.P. Chen, M. Jankowiak, N. Pradhan, T. Karaletsos, et al.

Journal of Machine Learning Research, 2019paper website arXiv '18

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

T. Karaletsos✶, T.D. Bui✶

NeurIPS 2020 ✶ equal contributionpaper arXiv '20

Bayesian Unsupervised Representation Learning with Oracle Constraints

T. Karaletsos, S. Belongie, G. Rätsch

ICLR 2016arXiv '15

Generalized Hidden Parameter MDPs: Transferable Model-Based RL in a Handful of Trials

C. Perez, F. Such, T. Karaletsos

AAAI 2020 (oral)paper arXiv '20

Black-Box Coreset Variational Inference

D. Manousakas✶, H. Ritter✶, T. Karaletsos ✶ equal contribution

NeurIPS 2022paper arXiv '22

Variational Control for Guidance in Diffusion Models

K. Pandey, F. Marouf Sofian, F. Draxler, T. Karaletsos, S. Mandt

ICML 2025paper arXiv '25

View all publications → · Google Scholar